tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

re-enable DPO for tests in modal ci (#1374)

Browse Source 
* re-enable DPO for tests in modal ci

* workaround for training args

* don't mixin AxolotlTrainingArguments

* fix mixin order so MRO doesn't result in

 TypeError: non-default argument follows default argument error

* use smaller datasets for dpo tests
This commit is contained in:
Wing Lian
2024-06-03 12:50:44 -04:00
committed by GitHub
parent 5cde06587a
commit 1f151c0d52
2 changed files with 19 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/axolotl/prompt_strategies/orpo/chat_template.py
View File

@@ -56,7 +56,9 @@ class ORPODatasetParsingStrategy:
messages: List[Message] = []
if system := prompt.get("system", None):
messages.append(Message(role="system", content=system, label=False))
messages.append(Message(role="user", content=prompt["prompt"], label=False))
messages.append(
Message(role="user", content=prompt["chosen"][0]["content"], label=False)
)
messages.append(
Message(
role="assistant", content=prompt["chosen"][1]["content"], label=True
@@ -70,7 +72,9 @@ class ORPODatasetParsingStrategy:
messages: List[Message] = []
if system := prompt.get("system", None):
messages.append(Message(role="system", content=system, label=False))
messages.append(Message(role="user", content=prompt["prompt"], label=False))
messages.append(
Message(role="user", content=prompt["rejected"][0]["content"], label=False)
)
messages.append(
Message(
role="assistant", content=prompt["rejected"][1]["content"], label=True
@@ -152,8 +156,8 @@ class ORPOTokenizingStrategy(PromptTokenizingStrategy):
def tokenize_prompt(self, prompt):
# pass the rejected prompt/row to the Prompter to get the formatted prompt
prompt_len = 0
rejected_message_list = self.dataset_parser.get_rejected_conversation_thread(
prompt
rejected_message_list: MessageList = (
self.dataset_parser.get_rejected_conversation_thread(prompt)
)
input_ids = []
labels = []
@@ -174,7 +178,9 @@ class ORPOTokenizingStrategy(PromptTokenizingStrategy):
rejected_input_ids = input_ids
rejected_labels = labels
# pass the chosen prompt/row to the Prompter to get the formatted prompt
chosen_message_list = self.dataset_parser.get_chosen_conversation_thread(prompt)
chosen_message_list: MessageList = (
self.dataset_parser.get_chosen_conversation_thread(prompt)
)
input_ids = []
labels = []
for _, (part, label) in enumerate(